© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12956
    Prev
    Next
    INDEX
    Explanations

    scientific writing relating to forces, interactions, and other physical phenomena, especially in quantum physics

    oai_token-act-pair · gemini-2.0-flash

    interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.78
    __':
    -0.75
    __*/
    -0.71
    richTextPanel
    -0.70
     getItemId
    -0.68
     unknownFields
    -0.67
    PhysRev
    -0.66
     auffi
    -0.65
     Efq
    -0.64
    ElementException
    -0.62
    POSITIVE LOGITS
    inquirer
    0.52
    epar
    0.49
     linear
    0.48
    overset
    0.47
     متعلقه
    0.46
     сра
    0.45
    >--}}
    0.45
     resourceCulture
    0.45
     />";
    0.45
    iencies
    0.44
    Activations Density 6.170%

    No Known Activations